{"id":"https://openalex.org/W4413144599","doi":"https://doi.org/10.1109/cvpr52734.2025.02603","title":"MotionPro: A Precise Motion Controller for Image-to-Video Generation*","display_name":"MotionPro: A Precise Motion Controller for Image-to-Video Generation*","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144599","doi":"https://doi.org/10.1109/cvpr52734.2025.02603"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027502276","display_name":"Zhongwei Zhang","orcid":"https://orcid.org/0000-0002-5776-5907"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwei Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036041413","display_name":"Fuchen Long","orcid":"https://orcid.org/0000-0003-0818-0985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuchen Long","raw_affiliation_strings":["HiDream.ai Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiDream.ai Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024833177","display_name":"Zhaofan Qiu","orcid":"https://orcid.org/0000-0002-7485-9198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaofan Qiu","raw_affiliation_strings":["HiDream.ai Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiDream.ai Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["HiDream.ai Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiDream.ai Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068917997","display_name":"Wu Liu","orcid":"https://orcid.org/0000-0003-1633-7575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Liu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiDream.ai Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101517779","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0002-5990-7307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiDream.ai Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27957","last_page":"27967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820420622825623},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6805687546730042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5762406587600708},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5070986747741699},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5027003288269043},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5023646354675293},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.47927138209342957},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.4133663773536682},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4056735932826996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820420622825623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6805687546730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5762406587600708},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5070986747741699},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5027003288269043},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5023646354675293},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.47927138209342957},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4133663773536682},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4056735932826996},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1579157894","https://openalex.org/W1967654336","https://openalex.org/W2060632806","https://openalex.org/W1530267862","https://openalex.org/W2995690499","https://openalex.org/W1494405360","https://openalex.org/W2050955821","https://openalex.org/W2153529351","https://openalex.org/W2040149295","https://openalex.org/W2016848112"],"abstract_inverted_index":{"Animating":[0],"images":[1],"with":[2,183],"interactive":[3],"motion":[4,23,35,53,61,66,71,133,147,156,169,197],"control":[5,36,119],"has":[6],"garnered":[7],"popularity":[8],"for":[9,188,217],"image-to-video":[10],"(I2V)":[11],"generation.":[12],"Modern":[13],"approaches":[14],"typically":[15],"rely":[16],"on":[17,86,202],"large":[18,109],"Gaussian":[19,110],"kernels":[20],"to":[21,33,39,63,100,143,213],"extend":[22],"trajectories":[24,99,123,167],"as":[25],"condition":[26],"without":[27],"explicitly":[28],"defining":[29],"movement":[30,151],"region,":[31],"leading":[32],"coarse":[34],"and":[37,42,60,68,94,168,194,204],"failing":[38],"disentangle":[40],"object":[41,74],"camera":[43,76],"moving.":[44],"To":[45,153],"alleviate":[46],"these,":[47],"we":[48,176],"present":[49],"MotionPro,":[50],"a":[51,91,179],"precise":[52,118],"controller":[54],"that":[55],"novelly":[56],"leverages":[57],"region-wise":[58,98,113,166],"trajectory":[59,114],"mask":[62,134,170],"regulate":[64],"fine-grained":[65,130,193],"synthesis":[67],"identify":[69],"target":[70],"category":[72],"(i.e.,":[73],"or":[75],"moving),":[77],"respectively.":[78],"Technically,":[79],"MotionPro":[80,158],"first":[81],"estimates":[82],"the":[83,97,139,145,150,189,207],"flow":[84,107,141],"maps":[85,142],"each":[87],"training":[88],"video":[89,161],"via":[90],"tracking":[92],"model,":[93],"then":[95],"samples":[96],"simulate":[101],"inference":[102],"scenario.":[103],"Instead":[104],"of":[105,149,191,209],"extending":[106],"through":[108,171],"kernels,":[111],"our":[112,214],"approach":[115],"enables":[116],"more":[117,218],"by":[120,163],"directly":[121],"utilizing":[122],"within":[124],"local":[125],"regions,":[126],"thereby":[127],"effectively":[128],"characterizing":[129],"movements.":[131],"A":[132],"is":[135],"simultaneously":[136],"derived":[137],"from":[138],"predicted":[140],"capture":[144],"holistic":[146],"dynamics":[148],"regions.":[152],"pursue":[154],"natural":[155],"control,":[157],"further":[159],"strengthens":[160],"denoising":[162],"incorporating":[164],"both":[165,192],"feature":[172],"modulation.":[173],"More":[174],"remarkably,":[175],"meticulously":[177],"construct":[178],"benchmark,":[180],"i.e.,":[181],"MC-Bench,":[182],"1.1K":[184],"user-annotated":[185],"image-trajectory":[186],"pairs,":[187],"evaluation":[190],"object-level":[195],"I2V":[196],"control.":[198],"Extensive":[199],"experiments":[200],"conducted":[201],"WebVid-10M":[203],"MC-Bench":[205],"demonstrate":[206],"effectiveness":[208],"MotionPro.":[210],"Please":[211],"refer":[212],"project":[215],"page":[216],"results:":[219],"https://zhw-zhang.github.io/MotionPro-page/.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}